[NeurIPS 2023] Latent Exploration for Reinforcement Learning
-
Updated
Feb 23, 2024 - Python
#
inductive-bias
Here are 10 public repositories matching this topic...
A phonosemantic grounding framework that uses Sanskrit articulatory phonology to create physically grounded AI embeddings. Includes clustering experiments on 150 Sanskrit verbal roots and a 10-dimensional coordinate system derived from speech production anatomy.
natural-language-processing representation-learning panini state-space-models interpretable-ai embodied-cognition sanskrit-grammar inductive-bias semantic-grounding phonosemantics source-filter-theory articulatory-phonology
-
Updated
Apr 19, 2026 - Jupyter Notebook
Repository of the paper "Learning complexity gradually in quantum machine learning models"
-
Updated
Nov 7, 2025 - Python
Comparison of CNN and Vision Transformer on custom MNIST/FashionMNIST datasets
python computer-vision deep-learning pytorch image-classification convolutional-neural-networks vision-transformer inductive-bias
-
Updated
Apr 25, 2026 - Python
[HiLD@ICML 2025] Memorization to generalization transition in diffusion models
-
Updated
Dec 19, 2025 - Python
Block-Term Operator Theory: why block-term rank-(L,L,1) neural operators generalize better than CP / Tucker / TT at matched capacity, not by more expressivity but as a tighter inductive bias. A least-squares generalization separation Theta((RL - mu_band) K / n), a complete variance-ordering theorem across all four tensor formats, an adaptive for...
machine-learning theory tensor-decomposition cp-decomposition random-matrix-theory tucker-decomposition double-descent operator-learning generalization-theory neural-operators fourier-neural-operator block-term-decomposition inductive-bias statistical-learning-theory
-
Updated
Jul 18, 2026 - Python
Hopf Latent Spaces: geometric inductive bias for neural networks. MSAI research + Karpathy autoresearch fork.
machine-learning research neural-networks hopf-fibration geometric-deep-learning msai inductive-bias autoresearch
-
Updated
Jul 2, 2026 - Python
An intuitive derivation of smoothing splines from variational calculus, demonstrating their relationship to reproducing kernel Hilbert spaces (RKHS) and regularized neural networks.
neural-network splines rkhs overparameterization reproducing-kernel-hilbert-space inductive-bias variational-calculus
-
Updated
Jul 31, 2026 - Python
At matched capacity, matching a spiking neuron to the signal physics beats neuron-type heterogeneity. Pure-SNN experiments on radar micro-Doppler (DIAT-µSAT) and audio (SHD) with a cross-domain double dissociation.
radar pytorch spiking-neural-networks reproducibility snn neuromorphic-computing micro-doppler inductive-bias surrogate-gradient double-dissociation spiking-heidelberg-digits
-
Updated
Jun 19, 2026 - Python
factorization-machines representation-learning embedding-models interaction-effect regression-analysis click-through-rate-prediction matching-function inductive-bias
-
Updated
Aug 13, 2026 - Jupyter Notebook
Add this topic to your repo
To associate your repository with the inductive-bias topic, visit your repo's landing page and select "manage topics."